{"work":{"id":"26c24caa-0134-405b-9fee-a8cf0c6a231e","openalex_id":"https://openalex.org/W4411113053","doi":"10.18653/v1/2025.findings-naacl.65","arxiv_id":null,"raw_key":null,"title":"2025 , pages =","authors":null,"authors_text":"Lu, Jiarui and Holleis, Thomas and Zhang, Yizhe and Aumayer, Bernhard and Nan, Feng and Bai, Haoping and Ma, Shuang and Ma, Shen and Li, Mengyu and Yin, Guoli and Wang, Zirui and Pang, Ruoming , editor =","year":2025,"venue":null,"abstract":null,"external_url":"https://doi.org/10.18653/v1/2025.findings-naacl.65","cited_by_count":6,"metadata_source":"openalex","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-20T05:23:03.143571+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":false,"display_title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities","render_title":"ToolSandbox: A Stateful, Conversational, Interactive Evaluation Benchmark for LLM Tool Use Capabilities"},"hub":{"state":{"tier_text":"hub","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":11,"external_cited_by_count":6},"tier":"hub","role_counts":[],"polarity_counts":[],"runs":{},"summary":{},"graph":{},"authors":[]}}